From 2ac34764a7783e635b1386df339b8edab18ff939 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 30 Sep 2026 23:33:23 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/llama3.2-3b-samantha-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++ README.md | 71 ++++++++++++++++++++++++++++++++ llama3.2-3b-samantha.IQ4_XS.gguf | 3 ++ llama3.2-3b-samantha.Q2_K.gguf | 3 ++ llama3.2-3b-samantha.Q3_K_L.gguf | 3 ++ llama3.2-3b-samantha.Q3_K_M.gguf | 3 ++ llama3.2-3b-samantha.Q3_K_S.gguf | 3 ++ llama3.2-3b-samantha.Q4_K_M.gguf | 3 ++ llama3.2-3b-samantha.Q4_K_S.gguf | 3 ++ llama3.2-3b-samantha.Q5_K_M.gguf | 3 ++ llama3.2-3b-samantha.Q5_K_S.gguf | 3 ++ llama3.2-3b-samantha.Q6_K.gguf | 3 ++ llama3.2-3b-samantha.Q8_0.gguf | 3 ++ llama3.2-3b-samantha.f16.gguf | 3 ++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 llama3.2-3b-samantha.IQ4_XS.gguf create mode 100644 llama3.2-3b-samantha.Q2_K.gguf create mode 100644 llama3.2-3b-samantha.Q3_K_L.gguf create mode 100644 llama3.2-3b-samantha.Q3_K_M.gguf create mode 100644 llama3.2-3b-samantha.Q3_K_S.gguf create mode 100644 llama3.2-3b-samantha.Q4_K_M.gguf create mode 100644 llama3.2-3b-samantha.Q4_K_S.gguf create mode 100644 llama3.2-3b-samantha.Q5_K_M.gguf create mode 100644 llama3.2-3b-samantha.Q5_K_S.gguf create mode 100644 llama3.2-3b-samantha.Q6_K.gguf create mode 100644 llama3.2-3b-samantha.Q8_0.gguf create mode 100644 llama3.2-3b-samantha.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..daad4bc --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-samantha.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0fc786 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: MOleg/llama3.2-3b-samantha +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/MOleg/llama3.2-3b-samantha + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-samantha-GGUF/resolve/main/llama3.2-3b-samantha.f16.gguf) | f16 | 6.5 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/llama3.2-3b-samantha.IQ4_XS.gguf b/llama3.2-3b-samantha.IQ4_XS.gguf new file mode 100644 index 0000000..3ad7a44 --- /dev/null +++ b/llama3.2-3b-samantha.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582e1acb8efc93d885172857289ffa317bc73388c4c4a5af6eb672d20f35cf7b +size 1840903488 diff --git a/llama3.2-3b-samantha.Q2_K.gguf b/llama3.2-3b-samantha.Q2_K.gguf new file mode 100644 index 0000000..4c8a09f --- /dev/null +++ b/llama3.2-3b-samantha.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b158b2ad073072db75ac22448429fd021a1b1a33bf282ba3e3525884e6dcdbdf +size 1363932480 diff --git a/llama3.2-3b-samantha.Q3_K_L.gguf b/llama3.2-3b-samantha.Q3_K_L.gguf new file mode 100644 index 0000000..dbccd71 --- /dev/null +++ b/llama3.2-3b-samantha.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bcbb5e3d91961307494ff65983a5bb570ccbfda4361fe2f38052a5e072a508 +size 1815344448 diff --git a/llama3.2-3b-samantha.Q3_K_M.gguf b/llama3.2-3b-samantha.Q3_K_M.gguf new file mode 100644 index 0000000..ecd8b8f --- /dev/null +++ b/llama3.2-3b-samantha.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397b58826a6dca7bc061a498794f4658d38e58575e645108e8511b2386fd0a8b +size 1687156032 diff --git a/llama3.2-3b-samantha.Q3_K_S.gguf b/llama3.2-3b-samantha.Q3_K_S.gguf new file mode 100644 index 0000000..9b18a5f --- /dev/null +++ b/llama3.2-3b-samantha.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eca47f78d1b385af60e299bc6e94aa9e8cd072d4ca50fb9593b886804143ea5 +size 1542845760 diff --git a/llama3.2-3b-samantha.Q4_K_M.gguf b/llama3.2-3b-samantha.Q4_K_M.gguf new file mode 100644 index 0000000..934885e --- /dev/null +++ b/llama3.2-3b-samantha.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5451bf26d43eee9ca665ec29992534d29f3d632ac99e3fa9861241821172e503 +size 2019374400 diff --git a/llama3.2-3b-samantha.Q4_K_S.gguf b/llama3.2-3b-samantha.Q4_K_S.gguf new file mode 100644 index 0000000..be4c1a3 --- /dev/null +++ b/llama3.2-3b-samantha.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5435fe387231d7fcbd09a452dbd54077d977f75e6ebe9a0bc5a67b8513471cef +size 1928197440 diff --git a/llama3.2-3b-samantha.Q5_K_M.gguf b/llama3.2-3b-samantha.Q5_K_M.gguf new file mode 100644 index 0000000..70b7b19 --- /dev/null +++ b/llama3.2-3b-samantha.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e93a9f2bc5770b38c9707372df091827db4512b79c45c2b4da747a2a6e1af40 +size 2322150720 diff --git a/llama3.2-3b-samantha.Q5_K_S.gguf b/llama3.2-3b-samantha.Q5_K_S.gguf new file mode 100644 index 0000000..f807462 --- /dev/null +++ b/llama3.2-3b-samantha.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da387306c77c07ce0be228f2bc951c88f0c6db2966e0dae0673e424e234f2a4e +size 2269508928 diff --git a/llama3.2-3b-samantha.Q6_K.gguf b/llama3.2-3b-samantha.Q6_K.gguf new file mode 100644 index 0000000..fbb3d98 --- /dev/null +++ b/llama3.2-3b-samantha.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac09749380b95445f2b94bf94ac87239cad353dcc46916238a84897c759386f +size 2643850560 diff --git a/llama3.2-3b-samantha.Q8_0.gguf b/llama3.2-3b-samantha.Q8_0.gguf new file mode 100644 index 0000000..a96ce69 --- /dev/null +++ b/llama3.2-3b-samantha.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adfc537cf27a4330de9826ce425c18b543351dbd2b5da34e0680cfcb11d54d3 +size 3421896000 diff --git a/llama3.2-3b-samantha.f16.gguf b/llama3.2-3b-samantha.f16.gguf new file mode 100644 index 0000000..eec6ffb --- /dev/null +++ b/llama3.2-3b-samantha.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1ebbd66c4e4d40f0b3ddd730368105d05d9ac63aef0cbaede98192dbc15332 +size 6433684800